torchrl 0.11.0__cp314-cp314-win_amd64.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (394) hide show
  1. benchmarks/benchmark_batched_envs.py +104 -0
  2. benchmarks/conftest.py +91 -0
  3. benchmarks/ecosystem/gym_env_throughput.py +321 -0
  4. benchmarks/ecosystem/vmas_rllib_vs_torchrl_sampling_performance.py +231 -0
  5. benchmarks/requirements.txt +7 -0
  6. benchmarks/storage/benchmark_sample_latency_over_rpc.py +193 -0
  7. benchmarks/test_collectors_benchmark.py +240 -0
  8. benchmarks/test_compressed_storage_benchmark.py +145 -0
  9. benchmarks/test_envs_benchmark.py +133 -0
  10. benchmarks/test_llm.py +101 -0
  11. benchmarks/test_non_tensor_env_benchmark.py +70 -0
  12. benchmarks/test_objectives_benchmarks.py +1199 -0
  13. benchmarks/test_replaybuffer_benchmark.py +254 -0
  14. sota-check/README.md +35 -0
  15. sota-implementations/README.md +142 -0
  16. sota-implementations/a2c/README.md +39 -0
  17. sota-implementations/a2c/a2c_atari.py +291 -0
  18. sota-implementations/a2c/a2c_mujoco.py +273 -0
  19. sota-implementations/a2c/utils_atari.py +240 -0
  20. sota-implementations/a2c/utils_mujoco.py +160 -0
  21. sota-implementations/bandits/README.md +7 -0
  22. sota-implementations/bandits/dqn.py +126 -0
  23. sota-implementations/cql/cql_offline.py +198 -0
  24. sota-implementations/cql/cql_online.py +249 -0
  25. sota-implementations/cql/discrete_cql_offline.py +180 -0
  26. sota-implementations/cql/discrete_cql_online.py +227 -0
  27. sota-implementations/cql/utils.py +471 -0
  28. sota-implementations/crossq/crossq.py +271 -0
  29. sota-implementations/crossq/utils.py +320 -0
  30. sota-implementations/ddpg/ddpg.py +231 -0
  31. sota-implementations/ddpg/utils.py +325 -0
  32. sota-implementations/decision_transformer/dt.py +163 -0
  33. sota-implementations/decision_transformer/lamb.py +167 -0
  34. sota-implementations/decision_transformer/online_dt.py +178 -0
  35. sota-implementations/decision_transformer/utils.py +562 -0
  36. sota-implementations/discrete_sac/discrete_sac.py +243 -0
  37. sota-implementations/discrete_sac/utils.py +324 -0
  38. sota-implementations/dqn/README.md +30 -0
  39. sota-implementations/dqn/dqn_atari.py +272 -0
  40. sota-implementations/dqn/dqn_cartpole.py +236 -0
  41. sota-implementations/dqn/utils_atari.py +132 -0
  42. sota-implementations/dqn/utils_cartpole.py +90 -0
  43. sota-implementations/dreamer/README.md +129 -0
  44. sota-implementations/dreamer/dreamer.py +586 -0
  45. sota-implementations/dreamer/dreamer_utils.py +1107 -0
  46. sota-implementations/expert-iteration/README.md +352 -0
  47. sota-implementations/expert-iteration/ei_utils.py +770 -0
  48. sota-implementations/expert-iteration/expert-iteration-async.py +512 -0
  49. sota-implementations/expert-iteration/expert-iteration-sync.py +508 -0
  50. sota-implementations/expert-iteration/requirements_gsm8k.txt +13 -0
  51. sota-implementations/expert-iteration/requirements_ifeval.txt +16 -0
  52. sota-implementations/gail/gail.py +327 -0
  53. sota-implementations/gail/gail_utils.py +68 -0
  54. sota-implementations/gail/ppo_utils.py +157 -0
  55. sota-implementations/grpo/README.md +273 -0
  56. sota-implementations/grpo/grpo-async.py +437 -0
  57. sota-implementations/grpo/grpo-sync.py +435 -0
  58. sota-implementations/grpo/grpo_utils.py +843 -0
  59. sota-implementations/grpo/requirements_gsm8k.txt +11 -0
  60. sota-implementations/grpo/requirements_ifeval.txt +16 -0
  61. sota-implementations/impala/README.md +33 -0
  62. sota-implementations/impala/impala_multi_node_ray.py +292 -0
  63. sota-implementations/impala/impala_multi_node_submitit.py +284 -0
  64. sota-implementations/impala/impala_single_node.py +261 -0
  65. sota-implementations/impala/utils.py +184 -0
  66. sota-implementations/iql/discrete_iql.py +230 -0
  67. sota-implementations/iql/iql_offline.py +164 -0
  68. sota-implementations/iql/iql_online.py +225 -0
  69. sota-implementations/iql/utils.py +437 -0
  70. sota-implementations/multiagent/README.md +74 -0
  71. sota-implementations/multiagent/iql.py +237 -0
  72. sota-implementations/multiagent/maddpg_iddpg.py +266 -0
  73. sota-implementations/multiagent/mappo_ippo.py +267 -0
  74. sota-implementations/multiagent/qmix_vdn.py +271 -0
  75. sota-implementations/multiagent/sac.py +337 -0
  76. sota-implementations/multiagent/utils/__init__.py +4 -0
  77. sota-implementations/multiagent/utils/logging.py +151 -0
  78. sota-implementations/multiagent/utils/utils.py +43 -0
  79. sota-implementations/ppo/README.md +29 -0
  80. sota-implementations/ppo/ppo_atari.py +305 -0
  81. sota-implementations/ppo/ppo_mujoco.py +293 -0
  82. sota-implementations/ppo/utils_atari.py +238 -0
  83. sota-implementations/ppo/utils_mujoco.py +152 -0
  84. sota-implementations/ppo_trainer/train.py +21 -0
  85. sota-implementations/redq/README.md +7 -0
  86. sota-implementations/redq/redq.py +199 -0
  87. sota-implementations/redq/utils.py +1060 -0
  88. sota-implementations/sac/sac-async.py +266 -0
  89. sota-implementations/sac/sac.py +239 -0
  90. sota-implementations/sac/utils.py +381 -0
  91. sota-implementations/sac_trainer/train.py +16 -0
  92. sota-implementations/td3/td3.py +254 -0
  93. sota-implementations/td3/utils.py +319 -0
  94. sota-implementations/td3_bc/td3_bc.py +177 -0
  95. sota-implementations/td3_bc/utils.py +251 -0
  96. torchrl/__init__.py +144 -0
  97. torchrl/_extension.py +74 -0
  98. torchrl/_torchrl.cp314-win_amd64.pyd +0 -0
  99. torchrl/_utils.py +1431 -0
  100. torchrl/collectors/__init__.py +48 -0
  101. torchrl/collectors/_base.py +1058 -0
  102. torchrl/collectors/_constants.py +88 -0
  103. torchrl/collectors/_multi_async.py +324 -0
  104. torchrl/collectors/_multi_base.py +1805 -0
  105. torchrl/collectors/_multi_sync.py +464 -0
  106. torchrl/collectors/_runner.py +581 -0
  107. torchrl/collectors/_single.py +2009 -0
  108. torchrl/collectors/_single_async.py +259 -0
  109. torchrl/collectors/collectors.py +62 -0
  110. torchrl/collectors/distributed/__init__.py +32 -0
  111. torchrl/collectors/distributed/default_configs.py +133 -0
  112. torchrl/collectors/distributed/generic.py +1306 -0
  113. torchrl/collectors/distributed/ray.py +1092 -0
  114. torchrl/collectors/distributed/rpc.py +1006 -0
  115. torchrl/collectors/distributed/sync.py +731 -0
  116. torchrl/collectors/distributed/utils.py +160 -0
  117. torchrl/collectors/llm/__init__.py +10 -0
  118. torchrl/collectors/llm/base.py +494 -0
  119. torchrl/collectors/llm/ray_collector.py +275 -0
  120. torchrl/collectors/llm/utils.py +36 -0
  121. torchrl/collectors/llm/weight_update/__init__.py +10 -0
  122. torchrl/collectors/llm/weight_update/vllm.py +348 -0
  123. torchrl/collectors/llm/weight_update/vllm_v2.py +311 -0
  124. torchrl/collectors/utils.py +433 -0
  125. torchrl/collectors/weight_update.py +591 -0
  126. torchrl/csrc/numpy_utils.h +38 -0
  127. torchrl/csrc/pybind.cpp +27 -0
  128. torchrl/csrc/segment_tree.h +458 -0
  129. torchrl/csrc/torch_utils.h +34 -0
  130. torchrl/csrc/utils.cpp +48 -0
  131. torchrl/csrc/utils.h +31 -0
  132. torchrl/data/__init__.py +187 -0
  133. torchrl/data/datasets/__init__.py +58 -0
  134. torchrl/data/datasets/atari_dqn.py +878 -0
  135. torchrl/data/datasets/common.py +281 -0
  136. torchrl/data/datasets/d4rl.py +489 -0
  137. torchrl/data/datasets/d4rl_infos.py +187 -0
  138. torchrl/data/datasets/gen_dgrl.py +375 -0
  139. torchrl/data/datasets/minari_data.py +643 -0
  140. torchrl/data/datasets/openml.py +177 -0
  141. torchrl/data/datasets/openx.py +798 -0
  142. torchrl/data/datasets/roboset.py +363 -0
  143. torchrl/data/datasets/utils.py +11 -0
  144. torchrl/data/datasets/vd4rl.py +432 -0
  145. torchrl/data/llm/__init__.py +34 -0
  146. torchrl/data/llm/dataset.py +491 -0
  147. torchrl/data/llm/history.py +1378 -0
  148. torchrl/data/llm/prompt.py +198 -0
  149. torchrl/data/llm/reward.py +225 -0
  150. torchrl/data/llm/topk.py +186 -0
  151. torchrl/data/llm/utils.py +543 -0
  152. torchrl/data/map/__init__.py +21 -0
  153. torchrl/data/map/hash.py +185 -0
  154. torchrl/data/map/query.py +204 -0
  155. torchrl/data/map/tdstorage.py +363 -0
  156. torchrl/data/map/tree.py +1434 -0
  157. torchrl/data/map/utils.py +103 -0
  158. torchrl/data/postprocs/__init__.py +8 -0
  159. torchrl/data/postprocs/postprocs.py +391 -0
  160. torchrl/data/replay_buffers/__init__.py +99 -0
  161. torchrl/data/replay_buffers/checkpointers.py +622 -0
  162. torchrl/data/replay_buffers/ray_buffer.py +292 -0
  163. torchrl/data/replay_buffers/replay_buffers.py +2376 -0
  164. torchrl/data/replay_buffers/samplers.py +2578 -0
  165. torchrl/data/replay_buffers/scheduler.py +265 -0
  166. torchrl/data/replay_buffers/storages.py +2412 -0
  167. torchrl/data/replay_buffers/utils.py +1042 -0
  168. torchrl/data/replay_buffers/writers.py +781 -0
  169. torchrl/data/tensor_specs.py +7101 -0
  170. torchrl/data/utils.py +334 -0
  171. torchrl/envs/__init__.py +265 -0
  172. torchrl/envs/async_envs.py +1105 -0
  173. torchrl/envs/batched_envs.py +3093 -0
  174. torchrl/envs/common.py +4241 -0
  175. torchrl/envs/custom/__init__.py +11 -0
  176. torchrl/envs/custom/chess.py +617 -0
  177. torchrl/envs/custom/llm.py +214 -0
  178. torchrl/envs/custom/pendulum.py +401 -0
  179. torchrl/envs/custom/san_moves.txt +29274 -0
  180. torchrl/envs/custom/tictactoeenv.py +288 -0
  181. torchrl/envs/env_creator.py +263 -0
  182. torchrl/envs/gym_like.py +752 -0
  183. torchrl/envs/libs/__init__.py +68 -0
  184. torchrl/envs/libs/_gym_utils.py +326 -0
  185. torchrl/envs/libs/brax.py +846 -0
  186. torchrl/envs/libs/dm_control.py +544 -0
  187. torchrl/envs/libs/envpool.py +447 -0
  188. torchrl/envs/libs/gym.py +2239 -0
  189. torchrl/envs/libs/habitat.py +138 -0
  190. torchrl/envs/libs/isaac_lab.py +87 -0
  191. torchrl/envs/libs/isaacgym.py +203 -0
  192. torchrl/envs/libs/jax_utils.py +166 -0
  193. torchrl/envs/libs/jumanji.py +963 -0
  194. torchrl/envs/libs/meltingpot.py +599 -0
  195. torchrl/envs/libs/openml.py +153 -0
  196. torchrl/envs/libs/openspiel.py +652 -0
  197. torchrl/envs/libs/pettingzoo.py +1042 -0
  198. torchrl/envs/libs/procgen.py +351 -0
  199. torchrl/envs/libs/robohive.py +429 -0
  200. torchrl/envs/libs/smacv2.py +645 -0
  201. torchrl/envs/libs/unity_mlagents.py +891 -0
  202. torchrl/envs/libs/utils.py +147 -0
  203. torchrl/envs/libs/vmas.py +813 -0
  204. torchrl/envs/llm/__init__.py +63 -0
  205. torchrl/envs/llm/chat.py +730 -0
  206. torchrl/envs/llm/datasets/README.md +4 -0
  207. torchrl/envs/llm/datasets/__init__.py +17 -0
  208. torchrl/envs/llm/datasets/gsm8k.py +353 -0
  209. torchrl/envs/llm/datasets/ifeval.py +274 -0
  210. torchrl/envs/llm/envs.py +789 -0
  211. torchrl/envs/llm/libs/README.md +3 -0
  212. torchrl/envs/llm/libs/__init__.py +8 -0
  213. torchrl/envs/llm/libs/mlgym.py +869 -0
  214. torchrl/envs/llm/reward/__init__.py +10 -0
  215. torchrl/envs/llm/reward/gsm8k.py +324 -0
  216. torchrl/envs/llm/reward/ifeval/README.md +13 -0
  217. torchrl/envs/llm/reward/ifeval/__init__.py +10 -0
  218. torchrl/envs/llm/reward/ifeval/_instructions.py +1667 -0
  219. torchrl/envs/llm/reward/ifeval/_instructions_main.py +131 -0
  220. torchrl/envs/llm/reward/ifeval/_instructions_registry.py +100 -0
  221. torchrl/envs/llm/reward/ifeval/_instructions_util.py +1677 -0
  222. torchrl/envs/llm/reward/ifeval/_scorer.py +454 -0
  223. torchrl/envs/llm/transforms/__init__.py +55 -0
  224. torchrl/envs/llm/transforms/browser.py +292 -0
  225. torchrl/envs/llm/transforms/dataloading.py +859 -0
  226. torchrl/envs/llm/transforms/format.py +73 -0
  227. torchrl/envs/llm/transforms/kl.py +1544 -0
  228. torchrl/envs/llm/transforms/policy_version.py +189 -0
  229. torchrl/envs/llm/transforms/reason.py +323 -0
  230. torchrl/envs/llm/transforms/tokenizer.py +321 -0
  231. torchrl/envs/llm/transforms/tools.py +1955 -0
  232. torchrl/envs/model_based/__init__.py +9 -0
  233. torchrl/envs/model_based/common.py +180 -0
  234. torchrl/envs/model_based/dreamer.py +112 -0
  235. torchrl/envs/transforms/__init__.py +147 -0
  236. torchrl/envs/transforms/functional.py +48 -0
  237. torchrl/envs/transforms/gym_transforms.py +203 -0
  238. torchrl/envs/transforms/module.py +341 -0
  239. torchrl/envs/transforms/r3m.py +372 -0
  240. torchrl/envs/transforms/ray_service.py +663 -0
  241. torchrl/envs/transforms/rb_transforms.py +214 -0
  242. torchrl/envs/transforms/transforms.py +11835 -0
  243. torchrl/envs/transforms/utils.py +94 -0
  244. torchrl/envs/transforms/vc1.py +307 -0
  245. torchrl/envs/transforms/vecnorm.py +845 -0
  246. torchrl/envs/transforms/vip.py +407 -0
  247. torchrl/envs/utils.py +1718 -0
  248. torchrl/envs/vec_envs.py +11 -0
  249. torchrl/modules/__init__.py +206 -0
  250. torchrl/modules/distributions/__init__.py +73 -0
  251. torchrl/modules/distributions/continuous.py +830 -0
  252. torchrl/modules/distributions/discrete.py +908 -0
  253. torchrl/modules/distributions/truncated_normal.py +187 -0
  254. torchrl/modules/distributions/utils.py +233 -0
  255. torchrl/modules/llm/__init__.py +62 -0
  256. torchrl/modules/llm/backends/__init__.py +65 -0
  257. torchrl/modules/llm/backends/vllm/__init__.py +94 -0
  258. torchrl/modules/llm/backends/vllm/_models.py +46 -0
  259. torchrl/modules/llm/backends/vllm/base.py +72 -0
  260. torchrl/modules/llm/backends/vllm/vllm_async.py +2075 -0
  261. torchrl/modules/llm/backends/vllm/vllm_plugin.py +22 -0
  262. torchrl/modules/llm/backends/vllm/vllm_sync.py +446 -0
  263. torchrl/modules/llm/backends/vllm/vllm_utils.py +129 -0
  264. torchrl/modules/llm/policies/__init__.py +28 -0
  265. torchrl/modules/llm/policies/common.py +1809 -0
  266. torchrl/modules/llm/policies/transformers_wrapper.py +2756 -0
  267. torchrl/modules/llm/policies/vllm_wrapper.py +2241 -0
  268. torchrl/modules/llm/utils.py +23 -0
  269. torchrl/modules/mcts/__init__.py +21 -0
  270. torchrl/modules/mcts/scores.py +579 -0
  271. torchrl/modules/models/__init__.py +86 -0
  272. torchrl/modules/models/batchrenorm.py +119 -0
  273. torchrl/modules/models/decision_transformer.py +179 -0
  274. torchrl/modules/models/exploration.py +731 -0
  275. torchrl/modules/models/llm.py +156 -0
  276. torchrl/modules/models/model_based.py +596 -0
  277. torchrl/modules/models/models.py +1712 -0
  278. torchrl/modules/models/multiagent.py +1067 -0
  279. torchrl/modules/models/recipes/impala.py +185 -0
  280. torchrl/modules/models/utils.py +162 -0
  281. torchrl/modules/planners/__init__.py +10 -0
  282. torchrl/modules/planners/cem.py +228 -0
  283. torchrl/modules/planners/common.py +73 -0
  284. torchrl/modules/planners/mppi.py +265 -0
  285. torchrl/modules/tensordict_module/__init__.py +89 -0
  286. torchrl/modules/tensordict_module/actors.py +2457 -0
  287. torchrl/modules/tensordict_module/common.py +529 -0
  288. torchrl/modules/tensordict_module/exploration.py +814 -0
  289. torchrl/modules/tensordict_module/probabilistic.py +321 -0
  290. torchrl/modules/tensordict_module/rnn.py +1639 -0
  291. torchrl/modules/tensordict_module/sequence.py +132 -0
  292. torchrl/modules/tensordict_module/world_models.py +34 -0
  293. torchrl/modules/utils/__init__.py +38 -0
  294. torchrl/modules/utils/mappings.py +9 -0
  295. torchrl/modules/utils/utils.py +89 -0
  296. torchrl/objectives/__init__.py +78 -0
  297. torchrl/objectives/a2c.py +659 -0
  298. torchrl/objectives/common.py +753 -0
  299. torchrl/objectives/cql.py +1346 -0
  300. torchrl/objectives/crossq.py +710 -0
  301. torchrl/objectives/ddpg.py +453 -0
  302. torchrl/objectives/decision_transformer.py +371 -0
  303. torchrl/objectives/deprecated.py +516 -0
  304. torchrl/objectives/dqn.py +683 -0
  305. torchrl/objectives/dreamer.py +488 -0
  306. torchrl/objectives/functional.py +48 -0
  307. torchrl/objectives/gail.py +258 -0
  308. torchrl/objectives/iql.py +996 -0
  309. torchrl/objectives/llm/__init__.py +30 -0
  310. torchrl/objectives/llm/grpo.py +846 -0
  311. torchrl/objectives/llm/sft.py +482 -0
  312. torchrl/objectives/multiagent/__init__.py +8 -0
  313. torchrl/objectives/multiagent/qmixer.py +396 -0
  314. torchrl/objectives/ppo.py +1669 -0
  315. torchrl/objectives/redq.py +683 -0
  316. torchrl/objectives/reinforce.py +530 -0
  317. torchrl/objectives/sac.py +1580 -0
  318. torchrl/objectives/td3.py +570 -0
  319. torchrl/objectives/td3_bc.py +625 -0
  320. torchrl/objectives/utils.py +782 -0
  321. torchrl/objectives/value/__init__.py +28 -0
  322. torchrl/objectives/value/advantages.py +1956 -0
  323. torchrl/objectives/value/functional.py +1459 -0
  324. torchrl/objectives/value/utils.py +360 -0
  325. torchrl/record/__init__.py +17 -0
  326. torchrl/record/loggers/__init__.py +23 -0
  327. torchrl/record/loggers/common.py +48 -0
  328. torchrl/record/loggers/csv.py +226 -0
  329. torchrl/record/loggers/mlflow.py +142 -0
  330. torchrl/record/loggers/tensorboard.py +139 -0
  331. torchrl/record/loggers/trackio.py +163 -0
  332. torchrl/record/loggers/utils.py +78 -0
  333. torchrl/record/loggers/wandb.py +214 -0
  334. torchrl/record/recorder.py +554 -0
  335. torchrl/services/__init__.py +79 -0
  336. torchrl/services/base.py +109 -0
  337. torchrl/services/ray_service.py +453 -0
  338. torchrl/testing/__init__.py +107 -0
  339. torchrl/testing/assertions.py +179 -0
  340. torchrl/testing/dist_utils.py +122 -0
  341. torchrl/testing/env_creators.py +227 -0
  342. torchrl/testing/env_helper.py +35 -0
  343. torchrl/testing/gym_helpers.py +156 -0
  344. torchrl/testing/llm_mocks.py +119 -0
  345. torchrl/testing/mocking_classes.py +2720 -0
  346. torchrl/testing/modules.py +295 -0
  347. torchrl/testing/mp_helpers.py +15 -0
  348. torchrl/testing/ray_helpers.py +293 -0
  349. torchrl/testing/utils.py +190 -0
  350. torchrl/trainers/__init__.py +42 -0
  351. torchrl/trainers/algorithms/__init__.py +11 -0
  352. torchrl/trainers/algorithms/configs/__init__.py +705 -0
  353. torchrl/trainers/algorithms/configs/collectors.py +216 -0
  354. torchrl/trainers/algorithms/configs/common.py +41 -0
  355. torchrl/trainers/algorithms/configs/data.py +308 -0
  356. torchrl/trainers/algorithms/configs/envs.py +104 -0
  357. torchrl/trainers/algorithms/configs/envs_libs.py +361 -0
  358. torchrl/trainers/algorithms/configs/logging.py +80 -0
  359. torchrl/trainers/algorithms/configs/modules.py +570 -0
  360. torchrl/trainers/algorithms/configs/objectives.py +177 -0
  361. torchrl/trainers/algorithms/configs/trainers.py +340 -0
  362. torchrl/trainers/algorithms/configs/transforms.py +955 -0
  363. torchrl/trainers/algorithms/configs/utils.py +252 -0
  364. torchrl/trainers/algorithms/configs/weight_sync_schemes.py +191 -0
  365. torchrl/trainers/algorithms/configs/weight_update.py +159 -0
  366. torchrl/trainers/algorithms/ppo.py +373 -0
  367. torchrl/trainers/algorithms/sac.py +308 -0
  368. torchrl/trainers/helpers/__init__.py +40 -0
  369. torchrl/trainers/helpers/collectors.py +416 -0
  370. torchrl/trainers/helpers/envs.py +573 -0
  371. torchrl/trainers/helpers/logger.py +33 -0
  372. torchrl/trainers/helpers/losses.py +132 -0
  373. torchrl/trainers/helpers/models.py +658 -0
  374. torchrl/trainers/helpers/replay_buffer.py +59 -0
  375. torchrl/trainers/helpers/trainers.py +301 -0
  376. torchrl/trainers/trainers.py +2052 -0
  377. torchrl/weight_update/__init__.py +33 -0
  378. torchrl/weight_update/_distributed.py +749 -0
  379. torchrl/weight_update/_mp.py +624 -0
  380. torchrl/weight_update/_noupdate.py +102 -0
  381. torchrl/weight_update/_ray.py +1032 -0
  382. torchrl/weight_update/_rpc.py +284 -0
  383. torchrl/weight_update/_shared.py +891 -0
  384. torchrl/weight_update/llm/__init__.py +32 -0
  385. torchrl/weight_update/llm/vllm_double_buffer.py +370 -0
  386. torchrl/weight_update/llm/vllm_nccl.py +710 -0
  387. torchrl/weight_update/utils.py +73 -0
  388. torchrl/weight_update/weight_sync_schemes.py +1244 -0
  389. torchrl-0.11.0.dist-info/LICENSE +21 -0
  390. torchrl-0.11.0.dist-info/METADATA +1307 -0
  391. torchrl-0.11.0.dist-info/RECORD +394 -0
  392. torchrl-0.11.0.dist-info/WHEEL +5 -0
  393. torchrl-0.11.0.dist-info/entry_points.txt +2 -0
  394. torchrl-0.11.0.dist-info/top_level.txt +7 -0
@@ -0,0 +1,394 @@
1
+ benchmarks\benchmark_batched_envs.py,sha256=lQojB0Ju7e7iAoj8eVR7kMQPuVGWCnRjnSUyUWvqfPU,3808
2
+ benchmarks\conftest.py,sha256=7PEuNk12k51EmsPMb3bM4PIEnL4WdArZXgtfd_RNBDg,2714
3
+ benchmarks\requirements.txt,sha256=zq-bWlShbTeSnj-Ud4NDgGngvWR_jdpnTAlMahTjr3k,74
4
+ benchmarks\test_collectors_benchmark.py,sha256=_Lq2P_p6r0GY-QsqUFC6x8d8jhA7Duh8SAx4BTJpwSI,6909
5
+ benchmarks\test_compressed_storage_benchmark.py,sha256=8NjVwRGKxi5CSuq9O9xLzM6MYG8R3a1afBjaXtGQjPY,6074
6
+ benchmarks\test_envs_benchmark.py,sha256=ntXAMgLSKtasErZso_lsM_F2ae6gnuBS-Ow0tI4OPoM,3653
7
+ benchmarks\test_llm.py,sha256=kHONY3smLA1JbyCBbSSeX8XSiapD6SiFxNKwikMf2-I,4038
8
+ benchmarks\test_non_tensor_env_benchmark.py,sha256=R2r74BBGlUyjYCbAoWK-K8oEzRdt68xYdSLF7OqmEtI,2413
9
+ benchmarks\test_objectives_benchmarks.py,sha256=mkl8VUD7CtRWa4Xwim6u7EdRTwlj7beoa47FpfTnrN4,36148
10
+ benchmarks\test_replaybuffer_benchmark.py,sha256=3VoDtjg0h3q76em1Ptq75jh_qfeHplYR4d3e1vTFsRc,8274
11
+ benchmarks\ecosystem\gym_env_throughput.py,sha256=DBPVsfzQtotVN0mwAFiPX5ZFxbNGlsaerIp7ZtvwHMk,14279
12
+ benchmarks\ecosystem\vmas_rllib_vs_torchrl_sampling_performance.py,sha256=TOM9A7GdcNBTBpF2vez9R_j7m38ttpZJvqcc-XHgzd0,6958
13
+ benchmarks\storage\benchmark_sample_latency_over_rpc.py,sha256=n4z0kOSo_Vk5cxWZJzHpUD6xGJ9Mq56Bqi9bAfJd4pI,6525
14
+ sota-check\README.md,sha256=SJD3LPaQ88eD5LpBmkC6C86uQxiM1DjEXXGIDbL5h6Q,1117
15
+ sota-implementations\README.md,sha256=COIu5bIwvXFM-yvQflX1SaYj9grjLwiUsbnEBskBfXE,3762
16
+ sota-implementations\a2c\a2c_atari.py,sha256=zdnSgvluVbt-ku3CtnTz-4SjER_2cq5GDDI9ZSqW0-c,9910
17
+ sota-implementations\a2c\a2c_mujoco.py,sha256=0TLUhKsH9eoKRRvAa4HAcvMChjd4-qC1WL9TZ706W6s,9520
18
+ sota-implementations\a2c\README.md,sha256=2A3JlM3dTOgBZXIPfLho7cQLq5EFRVJDkvQ1kdz6VnE,1771
19
+ sota-implementations\a2c\utils_atari.py,sha256=GU4vnfGQfJh3znaY29RJKkxMK15hEEZarZVTAwKPs-4,7215
20
+ sota-implementations\a2c\utils_mujoco.py,sha256=ekNpmeifgUK9TbbhIc8ZHT_JdqZkCiccYM6lGRfnwxY,5107
21
+ sota-implementations\bandits\dqn.py,sha256=COc0LCH1WqUFbQ4iAhffw6PrSZ_MVwCz50K2hG6VHhg,4325
22
+ sota-implementations\bandits\README.md,sha256=ChHg5-eB72m22qY1-9eJU3EKpQPuDvtclZuykeYjg6k,400
23
+ sota-implementations\cql\cql_offline.py,sha256=X5ChqeVxphwZjpa5mnXTP3QHdHyURm71I9bD1nWrMtg,6407
24
+ sota-implementations\cql\cql_online.py,sha256=J3bJURuZojxEmVIDmG6cozsSuR8opc5BJeKaJACMsuU,8671
25
+ sota-implementations\cql\discrete_cql_offline.py,sha256=R7nAVthj2XFHgScMS1gaOW-uP_18CUhZQHY4Q_BpsZ8,5872
26
+ sota-implementations\cql\discrete_cql_online.py,sha256=wa_x-UCI1lOJ_6wfxH_9AJl_n_yPNJdCxgFG-HSRtp0,7706
27
+ sota-implementations\cql\utils.py,sha256=qQ95LH7lPlrAAW5KbQDU1iaVLFW3yFN8SdpqpM6degs,14094
28
+ sota-implementations\crossq\crossq.py,sha256=se-rWWjjdpjsASJhndpM0ycWFSo9Ob2uOd5-Uecg-6w,9528
29
+ sota-implementations\crossq\utils.py,sha256=7U-ZRjYTZBUgtYGnCkjfoCAbx267tGH1kaxJ-zD3hRY,9579
30
+ sota-implementations\ddpg\ddpg.py,sha256=3U2uwD6zWWeXqMwMde6engsGSfUmUdw-8ogo3P1rIcQ,7761
31
+ sota-implementations\ddpg\utils.py,sha256=voA1ktFNFXIh1puMsiOjQ5kR5TAIK9vww4gUlsAUTVg,9159
32
+ sota-implementations\decision_transformer\dt.py,sha256=TR6DOrzjNt-tnAVxkm6EHEJMI09PPu05s7ctAQfDH2Y,5354
33
+ sota-implementations\decision_transformer\lamb.py,sha256=RAu7Hv_Rf_hNiPOyZUHrKB4LjnDFckwbU-JdLAwoY4A,7327
34
+ sota-implementations\decision_transformer\online_dt.py,sha256=6v0wLHpr3B7fDPxm-jKTbM-hU_I9RXxfJdU3D-dtbLY,6093
35
+ sota-implementations\decision_transformer\utils.py,sha256=oXuzHQoQT9KpXcorCaCim921LbKdeSXMhsYSsx_vXEc,16409
36
+ sota-implementations\discrete_sac\discrete_sac.py,sha256=5MO9yxyUW6BX9msJLFzwKP7dlGq7oOAxpwVQCHZgooM,8209
37
+ sota-implementations\discrete_sac\utils.py,sha256=m5xwXGkMYdag4WeJWwpRG7VaSTanDs_b5maFJUQtqZw,9520
38
+ sota-implementations\dqn\dqn_atari.py,sha256=604e2epvIcfsAIoqadviJTvvFZnuay2RQAc_FMD4rWE,9485
39
+ sota-implementations\dqn\dqn_cartpole.py,sha256=26JaxWryK--d66DnjpWNZjHRJSycmp7_euhRGR_Z-Ao,8602
40
+ sota-implementations\dqn\README.md,sha256=ROgJlTEW_4IeY5yC5E-6Sh-zGr-hZm3piIXvqNjj1f0,1305
41
+ sota-implementations\dqn\utils_atari.py,sha256=4n_ZDJBciIcQ97kgBs550aCgMul00KrsBdfieMXy4q0,4146
42
+ sota-implementations\dqn\utils_cartpole.py,sha256=RjRMS1RIGO7W5ojz_FdsTzs1HKg6ytn4mEydxMhh9oU,2931
43
+ sota-implementations\dreamer\dreamer.py,sha256=9VFUORRZa4Sl_D0zhGB4downM-V6mAGitB7RYeBjSBE,24689
44
+ sota-implementations\dreamer\dreamer_utils.py,sha256=OA8u-4jQQmI6Gd-n01FsrQpUuBCtlVsLfXTOHJTxQUE,37429
45
+ sota-implementations\dreamer\README.md,sha256=IPbpxLIT75xtMKU9l5cbp-Mr3FkjQqY6unfIRcXPGY0,4039
46
+ sota-implementations\expert-iteration\ei_utils.py,sha256=y9p9QUkqw-HTIzW8lyFJyu8xyWjW-3ZHbuRzAQXzwJM,29598
47
+ sota-implementations\expert-iteration\expert-iteration-async.py,sha256=yIYr1NSLgy6rKDvdzLn-0DX1kxZkKv7_kGljNhnIhJs,19179
48
+ sota-implementations\expert-iteration\expert-iteration-sync.py,sha256=M4HLg2u3vZOLe4Fw_8G9rMjGP0YnzYnJb4hyjO-EIGI,20188
49
+ sota-implementations\expert-iteration\README.md,sha256=R0hrAQBFeV6vO9gQdmX35ytyqKzJSS3tIQbC8xBAdaw,13465
50
+ sota-implementations\expert-iteration\requirements_gsm8k.txt,sha256=Og-Rr5H6PiEhj7Mt7N1x3KsnBmwZ8hrr1wBAnKsRTvQ,223
51
+ sota-implementations\expert-iteration\requirements_ifeval.txt,sha256=SXtv9tBgIjiotjF5y-KQxZBgu6zimEjV5335lstlCgM,277
52
+ sota-implementations\gail\gail.py,sha256=kCya0ANNMiXyb5ZKKrLBVjD4c_6zk85dvqgXn5qP8gY,11595
53
+ sota-implementations\gail\gail_utils.py,sha256=3HlPzXrkW32yRbN3aSkHlegGrTHFMEZbRLe0L3oD1W4,2186
54
+ sota-implementations\gail\ppo_utils.py,sha256=vGjyuqUFqfK-TruO1rX2iky0SNVXgBvRy5IGsvWM8t4,5076
55
+ sota-implementations\grpo\grpo-async.py,sha256=XRz3gXvQJDossdVlqnXHqKSytq2nM7v1dWxlZIfQIgI,16409
56
+ sota-implementations\grpo\grpo-sync.py,sha256=2uoGdIGe_EHOH-ID9QxHTO0TYoEABJYVaxJ1x-JHztk,16641
57
+ sota-implementations\grpo\grpo_utils.py,sha256=nMiKwV6sAid81LLKWFcCyMfi2WzEd8btFTPpHWzeCR8,32581
58
+ sota-implementations\grpo\README.md,sha256=1d-SizM7-v2GupkaTXdQdVhhw-2tBfPzWewd-t9qPsI,11725
59
+ sota-implementations\grpo\requirements_gsm8k.txt,sha256=dguY2OqyufVxTC2bTgQyHrYEMszbtJzYcX5Ku8zTmlQ,108
60
+ sota-implementations\grpo\requirements_ifeval.txt,sha256=-ua2cnzUPy0-Ls3jUTOvEUJ8hW5IuCQx4VuOe6c98ho,162
61
+ sota-implementations\impala\impala_multi_node_ray.py,sha256=cRFmiQ5DCshTcRsLUYrQOOx0HQ2tN1Ror8HpQB5i1aI,10703
62
+ sota-implementations\impala\impala_multi_node_submitit.py,sha256=uXA50J0CNKQ6WWOluuge7HGH3nz3rwTzxO2svZUZjzg,10228
63
+ sota-implementations\impala\impala_single_node.py,sha256=v8fYC-J9yfmjajI-L30kJ2349Uw-CwTRSQWAI4M5wiw,9143
64
+ sota-implementations\impala\README.md,sha256=-5sxqpnYqbru77SoQwvUWBuL9Osrh9eLNOLludvy_Hg,1603
65
+ sota-implementations\impala\utils.py,sha256=qEE3qlrKCGCJ4ij20WnNzw0DFcmp7W0o8FyAgUQ4GAg,5567
66
+ sota-implementations\iql\discrete_iql.py,sha256=S2FAMs49SQhQ1k81czKLmIrVrMZzTS35TsrK4uQeFCs,8110
67
+ sota-implementations\iql\iql_offline.py,sha256=NtvSCRQCIy-CIl9wR8MMDNJhmZYCFvqb0vRdOVKShv8,5173
68
+ sota-implementations\iql\iql_online.py,sha256=YjISp-Dc8khUcyMMECM-woyM06UVhjpe_U9YJN6HfJk,7842
69
+ sota-implementations\iql\utils.py,sha256=FHvkjeBKedEghQKdD7i8v21Zg89gh8A4IRQKfMNWWrE,13073
70
+ sota-implementations\multiagent\iql.py,sha256=x5oXmdvt37LNoEghmt-lxJkjEzdVRG1nplTfTn930pg,8234
71
+ sota-implementations\multiagent\maddpg_iddpg.py,sha256=zSwShK2teqmGh-sccFkC8uHSxAhloKn3a881trZuVEo,9268
72
+ sota-implementations\multiagent\mappo_ippo.py,sha256=NxlZgNNn-lLaC1zlo_5oiEfAOL8soy9y7s2SsapLZjE,9211
73
+ sota-implementations\multiagent\qmix_vdn.py,sha256=s_h9KN8lzmTBRWLllepFaFVFFHYE3sfApzDsipYd_Ok,9573
74
+ sota-implementations\multiagent\README.md,sha256=zaL_V6TliLv_fKYgiFBPBfHXVsXpXI50B-HfNviNgL0,2561
75
+ sota-implementations\multiagent\sac.py,sha256=HgReVDwsy_igew5X6QG1Q1-CPMOl8188APiy_dkW5_8,12251
76
+ sota-implementations\multiagent\utils\logging.py,sha256=kZflcTcYCXsUkh3vUl3mgFw9BZaOPy1JaNpj1w5TkfU,5349
77
+ sota-implementations\multiagent\utils\utils.py,sha256=GO9dlnAzg4wz5xDN58ErlE60Jnf5EN1GrGp3Fug5THU,1360
78
+ sota-implementations\multiagent\utils\__init__.py,sha256=5xRGSM4YMr794wxfVj_SQly2cyHNyhXTdXdWUZJoM2M,183
79
+ sota-implementations\ppo\ppo_atari.py,sha256=HvdLrv3AzXNAt96khvvCVvUvOp5aIdg8kPNjm2x8V0Q,11268
80
+ sota-implementations\ppo\ppo_mujoco.py,sha256=dkUz73_k2nVLs6BynCBoyZ4xOkxsjcDOUsZqV__CJ1Q,10828
81
+ sota-implementations\ppo\README.md,sha256=YP0ZM5_HTAFlmkFEHcKybPJ5yihseTw5eMV9BHZHPrE,1438
82
+ sota-implementations\ppo\utils_atari.py,sha256=asOs4tgUA6yeCLslrM8MRuWhTiEcEJpxzC80G_dajhc,7235
83
+ sota-implementations\ppo\utils_mujoco.py,sha256=Zh_PFD5GpdPlhb0jaXzBxwsMaPMW481UeVerUv1UAJ4,4957
84
+ sota-implementations\ppo_trainer\train.py,sha256=zBZgEkKRgJHjAKkLQ5duqvwUb4cMVhpJ_bnEJPbtgyo,667
85
+ sota-implementations\redq\README.md,sha256=6H6LVAwWy9uxuyWdsL2aq6cCMtqg2XksPKr_1WbKJco,397
86
+ sota-implementations\redq\redq.py,sha256=rnyeVcys-vY21ykIvQ2AINHQZDwEHrP5sY5tedVINM0,6319
87
+ sota-implementations\redq\utils.py,sha256=bSf9vFJViGPtqNpPLWdv50gps_FZVfHxcmxjt0BRDmY,40331
88
+ sota-implementations\sac\sac-async.py,sha256=1OWQ_FU7tuTNYlP0KbVSTGx5ydKzKLXndiJsUoH2sDc,9497
89
+ sota-implementations\sac\sac.py,sha256=byjN7pMbaxC2Rvts-djDs38qh3SmoPe7i-M3GhvpoIE,8234
90
+ sota-implementations\sac\utils.py,sha256=ooNiXqGlt3xHxJm3fWz3BL1psrVKQrLSSGUSNrh-Tzw,11494
91
+ sota-implementations\sac_trainer\train.py,sha256=nZVPVtzi1f57oAtRyiwGw1S0oqb0JbLqiyurX9e6A1w,481
92
+ sota-implementations\td3\td3.py,sha256=Go9mg-31q_zXC8Zs1TV1pciQO2BsQEjsOkEgt1XJqXg,8489
93
+ sota-implementations\td3\utils.py,sha256=AU18AXsfPXnsOOB7wKgo_5pe1wFobquJywnI0ay0oyY,9561
94
+ sota-implementations\td3_bc\td3_bc.py,sha256=FdLU9rHPuid2XJ-Pfn8rI848udxF4uRZDg_ZKi0hs28,5871
95
+ sota-implementations\td3_bc\utils.py,sha256=ZMMYehJP6KZaiiwTRlJRFKC528M49QhfEb_RAxaBj-U,6951
96
+ torchrl\_extension.py,sha256=PJuBZ0On6vgp7eNkVEQ1MckRePTHRIyDO8rgqjOSNKU,3294
97
+ torchrl\_torchrl.cp314-win_amd64.pyd,sha256=Gh7Fm-mo9P7FqIHDYFHpQnIX1RHwCOtFAdKFQIfWPa4,477184
98
+ torchrl\_utils.py,sha256=4Vriy9DpP10qLum-kezGEp2Nn-49c4m_us1gS5XO-vY,48808
99
+ torchrl\__init__.py,sha256=LNPAt8CK_GYzwCDEgcqNamZuDfkERMBaNxEXFO67qaw,4114
100
+ torchrl\collectors\collectors.py,sha256=Hc7GizQsMRct_HmQajNJvPJ8M5jOf01p7TI_2bOpLIE,1930
101
+ torchrl\collectors\utils.py,sha256=Na90XTBP7npczndldlFHTs-lnDXDO8IlICKW9BpA_no,17836
102
+ torchrl\collectors\weight_update.py,sha256=DVWlbUrX-PDjvOKyYJLXMi06Y4TNw-CX33I78tD2qFU,25171
103
+ torchrl\collectors\_base.py,sha256=p6sZa9RrB8Xk_c9Ke9tpDQmvAJU6diGYP989jJf5gEU,42788
104
+ torchrl\collectors\_constants.py,sha256=hvW7Jb2gyi0Gx9icxHF9ag2I9YMY8VYQjTeMI4UUztw,2817
105
+ torchrl\collectors\_multi_async.py,sha256=kTe2SK00hmWxYftW0gTxinZS_Qixvx7GA1S_evKUka4,14687
106
+ torchrl\collectors\_multi_base.py,sha256=A5UftbdsfQOj0JfpsAD5We_fbk6Gd60CpZqlaLfMm-4,88399
107
+ torchrl\collectors\_multi_sync.py,sha256=U1VGoryfyjwBC_jMHIEFuvFWTeo_5vyPtaxggLY8G0U,21000
108
+ torchrl\collectors\_runner.py,sha256=l-btC3oDslu5UGbAxIVZvcFrMN7PmBVPkwlKbPgQmlg,24764
109
+ torchrl\collectors\_single.py,sha256=f9ftEJNcUXpd6plWEFwAa1hZESxWznUm-wPDr_az2rI,91448
110
+ torchrl\collectors\_single_async.py,sha256=C8N05P7PwSU0QwE2EM1XLcYCadaGIX8e0fzZ46UNa4M,14498
111
+ torchrl\collectors\__init__.py,sha256=Iubb0PxC_zgQ93qgIOs0KLKbLxbQgUzbv5gW-XOj0sw,1473
112
+ torchrl\collectors\distributed\default_configs.py,sha256=8VhYQ2FLLlWP_1kL-VdkXEUoqXvtFX7ybso9QoW8600,4516
113
+ torchrl\collectors\distributed\generic.py,sha256=lM8ddmnAiZx3qIg7HCk-4hUlmPZCpkkAybeCYdYVavQ,59063
114
+ torchrl\collectors\distributed\ray.py,sha256=COV8oc2hRY91j3n4D2ul6sVDDeg-fzM1uxMMVz7HnD0,51969
115
+ torchrl\collectors\distributed\rpc.py,sha256=mhEoMV7uchYYEu9eYqyfYFx4AFKK20ApsM-O45pXYm4,45704
116
+ torchrl\collectors\distributed\sync.py,sha256=chvQqzNARa3EUg4FqMweQOBMOQZTu-5g8GmiqmGPcZw,32580
117
+ torchrl\collectors\distributed\utils.py,sha256=yCz5HK0VhT4VlblpY9uu_fd-h_VpnHNlKKcYZClJ6os,6619
118
+ torchrl\collectors\distributed\__init__.py,sha256=CyeD47TJJ8nRCrTJPm0GqLXE1I81Pm_BCo2BPJTKa-Q,990
119
+ torchrl\collectors\llm\base.py,sha256=GIVu7Zh00fUAv65FhxjazNZr3xhcj2gxTL3TYT7dZ6U,23339
120
+ torchrl\collectors\llm\ray_collector.py,sha256=6coW14x4kpsr9EtWQlYBG3QSkbltCGV2uFAh8NeGbAE,11964
121
+ torchrl\collectors\llm\utils.py,sha256=GnDY2cTu4XEdwqqhFCP4QWfS2tsgaLTy8nwpIaTEsQI,1184
122
+ torchrl\collectors\llm\__init__.py,sha256=aByyApMGMsi-vWn7Y5kaNNgq_r_ci4dBxRJJ2YOaCLQ,397
123
+ torchrl\collectors\llm\weight_update\vllm.py,sha256=x9qDkf5SFdoVpC-Tc_VPYBYpUXD9l9l2CYbL085LRL0,14087
124
+ torchrl\collectors\llm\weight_update\vllm_v2.py,sha256=MR02VjWCfeuT2pMAzvlRwSxqAe7jIRtcdrSiYdFxRKg,12355
125
+ torchrl\collectors\llm\weight_update\__init__.py,sha256=24sO6TOftpORDN1um-p2UFsGykz9PLc8Fm2SEZYAxg0,334
126
+ torchrl\csrc\numpy_utils.h,sha256=7_1eiJS-r3sQ2wbvuTzjO4gD-crJ6XjyYhJRNrkkR_E,959
127
+ torchrl\csrc\pybind.cpp,sha256=k4XcgxL8V64hHM8ukPfjSwEdSEIdZPv8j-E2d_IGw38,757
128
+ torchrl\csrc\segment_tree.h,sha256=KFlOdosVXw19UCQabk4A1E-6bwcs9EffsAHzbB-jO00,17833
129
+ torchrl\csrc\torch_utils.h,sha256=k7gTjLle9wW_TG6GrqqOYIG1MKsWqjHPcoqPDxLys5Y,730
130
+ torchrl\csrc\utils.cpp,sha256=agOkJ0G4ytRsuGmkTXT1kBLGWOxrpkd6LHDVeZymEgA,1690
131
+ torchrl\csrc\utils.h,sha256=bXlPW94HH4UMRDXXbPgfC25SvI_txvAkueBmSex9g7M,1132
132
+ torchrl\data\tensor_specs.py,sha256=Gnev4BwnNGPeb7TDHS5rLKbH-o0o9O-S6qFierU90eI,265213
133
+ torchrl\data\utils.py,sha256=w768OxLHI0Ed1Ipb0Q7JPsToxRzjr2En4RnfZsc-Qtw,12441
134
+ torchrl\data\__init__.py,sha256=HzK7lNsV00H92fYqZaJlHKbPSOP_uulRcoMFnr8h9d0,4450
135
+ torchrl\data\datasets\atari_dqn.py,sha256=zet-dUhsxIbPNMqcbqksMCBSP9-ZvzIqxsviRaRTJtY,41626
136
+ torchrl\data\datasets\common.py,sha256=zp3tPuJ5tb3OVJlMljWg2bDslxbyfjmhpMNSq1Hm7VQ,16301
137
+ torchrl\data\datasets\d4rl.py,sha256=IJ47YwR0EyqaZte5MG1dKBlHy2tw-KpquUmkB1y3p0A,20688
138
+ torchrl\data\datasets\d4rl_infos.py,sha256=GYWrKvteI7wKYclBoggHpnvbMytfOTwhP3Gpr4TbMnA,22757
139
+ torchrl\data\datasets\gen_dgrl.py,sha256=h8P-7yGTDjDNs5EYFCGK-EJyCZvFNCFfgEyY1xf_M28,14668
140
+ torchrl\data\datasets\minari_data.py,sha256=Nr0LK_tSjXAOB_ZtxAzzAOmh3DuQxiEg0UC4QBtpLDc,29068
141
+ torchrl\data\datasets\openml.py,sha256=U6w_BrZlFvxA-3bfOOID5REYSf46IYKu92OlHK3VaXc,7195
142
+ torchrl\data\datasets\openx.py,sha256=onPQ2U24YuJ64juPVWWEZkS7C-ABkETsx8QKtQc4New,34428
143
+ torchrl\data\datasets\roboset.py,sha256=_ui7XN2108vhO1lKKoN0IbH77evRz5Ou7C3BCCE8V50,17020
144
+ torchrl\data\datasets\utils.py,sha256=tRZkarWl-BX_fnGEVNRt6Fjo0wmyKCNAuVmw5Le-0C4,350
145
+ torchrl\data\datasets\vd4rl.py,sha256=l7h2_rO56K4AbhKDYDojqmnXREONshnxVnARECpjJKU,18703
146
+ torchrl\data\datasets\__init__.py,sha256=LU-Xlf6tjUt7t1v0I3iDtnAPqdUCTDwsRj_Mr3E_9aI,1352
147
+ torchrl\data\llm\dataset.py,sha256=KoLfIQVwoJAHoa7mUs83exN4Ozpu_MTZpEDj5CqU97Q,21203
148
+ torchrl\data\llm\history.py,sha256=cYs4fYxp2jPAoFYRH1w1W-5UwNfxyNrNqvZeiXNFm7M,60844
149
+ torchrl\data\llm\prompt.py,sha256=ikHWafhTIoCONCpuMHwIuGfpnPSpg5drZQTxTCmygQE,8578
150
+ torchrl\data\llm\reward.py,sha256=QW1HWpNRORd3InwWLg-hAhjTlPqX4ffzAkYHEz0jQxo,8629
151
+ torchrl\data\llm\topk.py,sha256=E5rrMw_dXBpFsV_6DOwVSd714G6IKwjIxBZLpssmWLw,8551
152
+ torchrl\data\llm\utils.py,sha256=K2NQoEhBC6VWowsMeDHu2Q8vbg3ZPEWBBN6z4qifiNM,24143
153
+ torchrl\data\llm\__init__.py,sha256=-_UPiaQgHzFVLM_gfiOS0sCGVRwkxZ1_Z5B6C9ThN9o,1009
154
+ torchrl\data\map\hash.py,sha256=AilOzYQ0KYhCZpVZCm63AhRuXn2P_RLB4PcbIx6qnlA,7446
155
+ torchrl\data\map\query.py,sha256=CfAC9XJh7KpdCJNgqfJ5CUCi7BWqekgCMlNVSIF60To,8125
156
+ torchrl\data\map\tdstorage.py,sha256=HzdR7M8Fjt9543vqdEpy0QQ8tHgKLCqWYCA6P02_2dM,15143
157
+ torchrl\data\map\tree.py,sha256=EhYin_p5qRfb1mrfD_1mkYelyNupq4upMRaRPIvPLUY,60782
158
+ torchrl\data\map\utils.py,sha256=fEjqCzaE4Vqjb8OzUvnClmLxVMooqeFOBMs7wroYvxs,3022
159
+ torchrl\data\map\__init__.py,sha256=bON0vqCksU7FPoWNqiNcdl60t7yWUh9SdLhNtglj7jI,576
160
+ torchrl\data\postprocs\postprocs.py,sha256=kNkWUGDzuvW30tAW9k2p_WdAAZS7y7lrK5vidmpE6pA,15543
161
+ torchrl\data\postprocs\__init__.py,sha256=fOyX5OMaDb5HGrQbn9W72_QwncNdh6l3DkVSqRfNr4E,278
162
+ torchrl\data\replay_buffers\checkpointers.py,sha256=cPye6s15uPx3Q9YeH5jDH8wtVD8E8uyBLzclEQnTjYw,24207
163
+ torchrl\data\replay_buffers\ray_buffer.py,sha256=4rgImqxHrF5q-uPAFwUq5PF0xugkuEUo1p32wSXu7iw,10687
164
+ torchrl\data\replay_buffers\replay_buffers.py,sha256=v6gHqmr1tMCrnKMnY9OtGQr96x0FIQW9e8BjQ7DJkXs,104193
165
+ torchrl\data\replay_buffers\samplers.py,sha256=Cs2ekM8Mmwn6y3cu47AL4Sz-HAQ-DtGMbaICsZR5A_Q,114383
166
+ torchrl\data\replay_buffers\scheduler.py,sha256=SYJJSo7AFybzpPlj9Q1Bdsws3ZDkxokEaKxt4ZJPHbs,10444
167
+ torchrl\data\replay_buffers\storages.py,sha256=2cpvno_sAwlvTp1BpxANYaNHWaz0GAjwWdUWq5_lq08,94849
168
+ torchrl\data\replay_buffers\utils.py,sha256=Fvev7pyMx_vwzKAo0uGXfLy56-dBRQFGmJvv6OA1wQM,39640
169
+ torchrl\data\replay_buffers\writers.py,sha256=9E4YlS5MeS3I5Cplgb_eMsMIYwMehFYPE5lOYcpxK0Y,30494
170
+ torchrl\data\replay_buffers\__init__.py,sha256=RcJSEXHz6zt1gQSFhEaKwQHUhZkYa2x-buNSDkNAslE,2595
171
+ torchrl\envs\async_envs.py,sha256=bP6W_G0WY4tEqsVNCmrVOkluFO1LBUzXe7GNmJJoE6c,47244
172
+ torchrl\envs\batched_envs.py,sha256=EUATvHbDVFLAwEb7a5PDB0YC5PWP58tdO0cyGq3N6XM,134527
173
+ torchrl\envs\common.py,sha256=dHY3d1Dyzu9cRzujMNolB862ixk79jcQ3SoQ7T77azc,181701
174
+ torchrl\envs\env_creator.py,sha256=hZPA_kxJReQtTDsCp10EEa-Qc-ctSxxcKxoMvJD9Xno,10571
175
+ torchrl\envs\gym_like.py,sha256=dky7JLsHAVnTdLimf4KAZGsPP104SFLD4fVzlmyAYh8,32381
176
+ torchrl\envs\utils.py,sha256=6P9PfrYTxj65aLE-fEmPTmnb56BosTzYd_WTWPQ-q8I,73932
177
+ torchrl\envs\vec_envs.py,sha256=B3lrPCVk4jRIXy0V0berwktZInHpx_UBABTcPUlA1Lw,377
178
+ torchrl\envs\__init__.py,sha256=iTl9xrjI29A7zzCDKVCNx8ZpXjNtbme7r0GkRFMYmQU,6072
179
+ torchrl\envs\custom\chess.py,sha256=oWdMgE9DqZooAi7e16ryTMSMk4wFcbfnHxOyYUTgqkU,25280
180
+ torchrl\envs\custom\llm.py,sha256=FnZltPFKQUOH49qlvABk9dth2d2ZRkO_tiA0kiu6LKs,8869
181
+ torchrl\envs\custom\pendulum.py,sha256=8sBgT8DvHrg5-YSOduC8GAHM9v7SXXfd8BzHvQ3wHOU,18617
182
+ torchrl\envs\custom\san_moves.txt,sha256=AMStL2XCAnEbO6UZEYfDSCp5zRO2811gPEIzOWbmmRY,217492
183
+ torchrl\envs\custom\tictactoeenv.py,sha256=voszQ7rPl7PbCBB6BQ8OELCi5US5YFm5gb-CLOkAIRM,12547
184
+ torchrl\envs\custom\__init__.py,sha256=ykEXd0w3bXxzINWSa5dq0bEvk9OWuNF5OVdRjguYQAA,395
185
+ torchrl\envs\libs\brax.py,sha256=wZFSjJPdTEEMcP2s5PSXhofJh46Zig_FCTIoeU6OpAQ,32031
186
+ torchrl\envs\libs\dm_control.py,sha256=1O5b7neOLaA0sK2jQwVpv_ixh_4ELIt-j-eXBNEvDdo,23126
187
+ torchrl\envs\libs\envpool.py,sha256=bP7ocZ_ZVOJj49OxNN0hhm3WfNptS4MHeL1Yc9RL6TU,18466
188
+ torchrl\envs\libs\gym.py,sha256=sP4nztptvDY0GhGQEi44YCDmAnZf1yAOGsGyjfnlzbQ,90876
189
+ torchrl\envs\libs\habitat.py,sha256=w_B1VQQRcjH0kbynu6H9zcimjoluEqVcsH1P0WuQguM,5525
190
+ torchrl\envs\libs\isaacgym.py,sha256=C9fY_gLTRm1qk0TGMFMQKXNS27HBpIqRz2rjdJ0Lg7k,7336
191
+ torchrl\envs\libs\isaac_lab.py,sha256=lD3PVhuco2mncgSK-714yPQ9EjxdLOKRfDRR__eARec,3523
192
+ torchrl\envs\libs\jax_utils.py,sha256=q06IOxSX0jCfm1JnVGj-SldYHtUrlVoKtZj8U1zDJcI,6247
193
+ torchrl\envs\libs\jumanji.py,sha256=6C9NmILOt3wbgoEB4oHaDU-4lBRzJGQKJ62hYU8GLTg,41234
194
+ torchrl\envs\libs\meltingpot.py,sha256=5IT7Kj5C6u1CWDAdb1SimCgEv33ti1Y7hVsJy5Nf8bA,26695
195
+ torchrl\envs\libs\openml.py,sha256=DDG5qbBe7ipjQ8nJUg6pBVja8w9zsRJFY6n_m10zItg,5866
196
+ torchrl\envs\libs\openspiel.py,sha256=khtzdaQcJ7DsLdRZp0HW6X_lHuDwvPFZwyQBdiVEdfs,25453
197
+ torchrl\envs\libs\pettingzoo.py,sha256=F80ICfgSPB_w9al_tqfjqr8JBWMk3fqnysO0blFn73c,47658
198
+ torchrl\envs\libs\procgen.py,sha256=AxoOLqkfZKKpRGftTpvOO21GrdlckmnC2LHFGLaVwmw,14104
199
+ torchrl\envs\libs\robohive.py,sha256=_lFdaE87s-zgIfUmvtnmv5mPKq2u32OSxFQ_C7d1xAo,16228
200
+ torchrl\envs\libs\smacv2.py,sha256=30dGNvOkJ-Qx4XeyxN9lWsjGUYiPDY47fsOOrX76Zng,29693
201
+ torchrl\envs\libs\unity_mlagents.py,sha256=vszCYjEX0S9AmIwLvGsoqc0Jr7jvlBAqZ1HQ1uqesjM,50558
202
+ torchrl\envs\libs\utils.py,sha256=Ce8nAYc2MQOBTYCV17Yswk98pg3PStnaGPFVW2jqARQ,5354
203
+ torchrl\envs\libs\vmas.py,sha256=iXkPt0BJMXZphwefzm1C2E1RUhZ-fZ9w7Bc8eodCeiE,36229
204
+ torchrl\envs\libs\_gym_utils.py,sha256=JYCNtWW4gAYwLq4k87ZdwLtDR_mRSyWQOi4seuXllOI,13150
205
+ torchrl\envs\libs\__init__.py,sha256=2_DNKttWak967uFtG6i3Io9xJl9xhduYSBQCA1g-xXo,1912
206
+ torchrl\envs\llm\chat.py,sha256=vCtRIhlw_8jQ55KL8x8-7N9dXxb83z68MirCD2jqt6E,32529
207
+ torchrl\envs\llm\envs.py,sha256=OfaEnQRXoTaXOJgeZfSdQBHj1VkG6Gi1NOyg3Rmyq9k,35813
208
+ torchrl\envs\llm\__init__.py,sha256=mxvPV4WD_jViongRHTYScOHwwGPjUjKhch90jA11IuY,1504
209
+ torchrl\envs\llm\datasets\gsm8k.py,sha256=Mswwb_5kreT2AsV_MFaDrPw7qouSvFepqi4zG4k7Ngw,17054
210
+ torchrl\envs\llm\datasets\ifeval.py,sha256=9uSTySm3PKDIsgX7axHI1b-Z2IZmcNzUIACAIoDXuQM,12373
211
+ torchrl\envs\llm\datasets\README.md,sha256=NR7sJvHQ1Wf28-pWJ9LhfiKeqbmXzPpFnEiZIYuEP34,116
212
+ torchrl\envs\llm\datasets\__init__.py,sha256=6-x0WlKD7lpMVLKA4W1AktvgUs6adMuaGAqYYhgQ_hk,490
213
+ torchrl\envs\llm\libs\mlgym.py,sha256=2BGSiNUoKciKN5FD3s0MBisVJ6onBugJ6O8oZxoSddY,32316
214
+ torchrl\envs\llm\libs\README.md,sha256=qToAicfcmYsSe3TCc5o0lEsDmz84nt4GSIG0J_mOd_s,93
215
+ torchrl\envs\llm\libs\__init__.py,sha256=zvUe6oe3pjZwGefV-_x4MAC6K89TMqxh3TZs5s3ADkI,274
216
+ torchrl\envs\llm\reward\gsm8k.py,sha256=QKZtS8v2PWGnlSK9jasKAul9AskxFbV4W2SqeLaY6M0,13516
217
+ torchrl\envs\llm\reward\__init__.py,sha256=KYNJxyDOe2mZkjyH4CSuQ8qM0_Zu3EAaIGocYhLduPQ,380
218
+ torchrl\envs\llm\reward\ifeval\README.md,sha256=t4U5C_qZLOQbBDX2LE-PREcUyesgTKAK0bvI8WBezPI,815
219
+ torchrl\envs\llm\reward\ifeval\_instructions.py,sha256=t0nbq2z2pfoBgxowe4K031i35FT-QB_NnbPVppIxd-s,63384
220
+ torchrl\envs\llm\reward\ifeval\_instructions_main.py,sha256=oEwbiaFzEqaus9H39pbQw4GvT_tPhKvy7twEkZ4JdOg,4429
221
+ torchrl\envs\llm\reward\ifeval\_instructions_registry.py,sha256=bY8R51RgjKJYiim67j5IXSfYhtWtvZrRF61yuqi0Tzs,3914
222
+ torchrl\envs\llm\reward\ifeval\_instructions_util.py,sha256=9jhEQYzrnXQCKt0T0A6rZFxpTwn0yvzvO-yg9T5ADq0,27701
223
+ torchrl\envs\llm\reward\ifeval\_scorer.py,sha256=otF9AqjaZiD26TZG_XWkZ_aRUma0Wa54JSLXKWS8qNw,18306
224
+ torchrl\envs\llm\reward\ifeval\__init__.py,sha256=vvh7JSUQaEiMjNeMeJvWlcFb2-6_J1LfM6l4mENn4Zg,324
225
+ torchrl\envs\llm\transforms\browser.py,sha256=xs84IUzkHNrWmhBZVwPe-9BxZ07HER4JOxRZqnYxKhk,10737
226
+ torchrl\envs\llm\transforms\dataloading.py,sha256=Apjdtl_XNizDBEJzvfx2biQEguHjmdHS8eu58761Y10,38943
227
+ torchrl\envs\llm\transforms\format.py,sha256=tME390wkG0h2V5DAWHZa7EhJ5Or-6cga6AIjxPuy1l8,2592
228
+ torchrl\envs\llm\transforms\kl.py,sha256=aKT8eaf6Rqj1aXc5wETTFziAcfauUJTwqHMaN3XIcH4,72491
229
+ torchrl\envs\llm\transforms\policy_version.py,sha256=tAE58ZsDV9hgiLdJtysMoNIe_tEoxGrQYXrQrX-hnfU,7152
230
+ torchrl\envs\llm\transforms\reason.py,sha256=In7SSx5b0AO_HZKZsFKuJw-Kudg0wunOOczUEoqIlwc,14084
231
+ torchrl\envs\llm\transforms\tokenizer.py,sha256=KywECBywj34sJJWu1DR-KKa5jF_k0peyBCwqDrh2p_Q,14283
232
+ torchrl\envs\llm\transforms\tools.py,sha256=Ydf-VnXgUWpXuqnY53yB2vaRzGNKPV0fxLHDX2LiYCQ,74160
233
+ torchrl\envs\llm\transforms\__init__.py,sha256=x2ezLXEf2taPiK8XWFgmBwCNlkmgxx5_xN1aFhSLUxQ,1404
234
+ torchrl\envs\model_based\common.py,sha256=hrzZ0TouX62UnbQ7LEpH4hut5wpI0vW7Tjl2bjeGtK4,7972
235
+ torchrl\envs\model_based\dreamer.py,sha256=GgHF07BfWn1bnacrNptpe81I1l45ym5WIuYlmukqWgc,4377
236
+ torchrl\envs\model_based\__init__.py,sha256=4hObCadhqKPjUQ9WUdaXIsaeeivo_1N1d1h28TKzR74,340
237
+ torchrl\envs\transforms\functional.py,sha256=U8eTymhG_88oqPHdlQhJTsNHyY0fk9ouIMzr1OSgeyM,1486
238
+ torchrl\envs\transforms\gym_transforms.py,sha256=MS-PpSLLzdUFcvlF-yQkepwyBnmi7m9ivrDb2wSsVjM,10085
239
+ torchrl\envs\transforms\module.py,sha256=SzFwiJuOi7YdkTBd0SKFKtAAMx76oeCVSJnff6AdKLU,14582
240
+ torchrl\envs\transforms\r3m.py,sha256=3B-JB3GHh3s1Af69WZ3wl3BU8SP0g_QmuH8IPztXRbQ,13850
241
+ torchrl\envs\transforms\ray_service.py,sha256=PJmR525CNe8zvcSM3Ir6uPKxJD3HHKE9JA0ss1oGu_Y,23777
242
+ torchrl\envs\transforms\rb_transforms.py,sha256=eoJVEOv2ckVHth7nBgRaULW4TICf7YoQHcbWn9n1Cns,7661
243
+ torchrl\envs\transforms\transforms.py,sha256=rqHmlNlPWJfh39cXn4cjPeuBRaCgnKXAvtsFfczrcSk,509056
244
+ torchrl\envs\transforms\utils.py,sha256=V7YAV2BcJWvhC6aUV9LcwOodZFPbKmsltyR747OdRTU,3358
245
+ torchrl\envs\transforms\vc1.py,sha256=snXdONyRKkyMiaW-bT7SwDJUQVb5GWr1mqY1W78Ohn0,10841
246
+ torchrl\envs\transforms\vecnorm.py,sha256=jM5f0KZxn6p7gO2Q4HsYwxrB-HnsBcnmR2bC2BqQZKo,36226
247
+ torchrl\envs\transforms\vip.py,sha256=YpoMMOAXd4Wst3wcDynWb6bjaai2u87XeS9JMTseTtQ,15164
248
+ torchrl\envs\transforms\__init__.py,sha256=Qr3l1u5nEFDrxVzfVC4u17j3YMKMrQhciqai8zXCsOY,3338
249
+ torchrl\modules\__init__.py,sha256=PdsVLKJPb37xeKyxLfrPvB0PtBPJVpgJCYoQPq5UNwE,4774
250
+ torchrl\modules\distributions\continuous.py,sha256=Hl_u1myH-grzspveQBf3We1k7VIVmwHGvmPrODTYXlM,30363
251
+ torchrl\modules\distributions\discrete.py,sha256=7nofDnfocF3asl3RtWUy7m2ME1ezZUk4-NnmZ1j-5lc,36498
252
+ torchrl\modules\distributions\truncated_normal.py,sha256=IXreZTo7azCHcgMP2ND0hbJXRHx2wYGHbQKuiI-cNo8,6402
253
+ torchrl\modules\distributions\utils.py,sha256=7hJSAKTnL6KUcFdGwfMRvmTS4CLXTM3uAQd49hjcHcw,8054
254
+ torchrl\modules\distributions\__init__.py,sha256=Evkiz96ZPs7VUZp2n03h9kd7rmUCEEvMVl2f7RhzMhQ,1670
255
+ torchrl\modules\llm\utils.py,sha256=b2s9ngHwXnNbLggygU3-ScNwk0MWICketq2pZBshGqM,749
256
+ torchrl\modules\llm\__init__.py,sha256=N2w5lIWcubs2w9K8ydKsI5ENR-aQY2bt5IRv_bh4kyU,1925
257
+ torchrl\modules\llm\backends\__init__.py,sha256=AU-CwH7kcgQw1JUJaeQYjzRxKrlqMxZoK5zGw80xus8,2207
258
+ torchrl\modules\llm\backends\vllm\base.py,sha256=KZs36Q0sNveEkHJrub6xD_SzZafAdWz5ZK5ssHphMHM,2149
259
+ torchrl\modules\llm\backends\vllm\vllm_async.py,sha256=fRTVusV3KPK5qA4R6k-GUX_r2MkNJg75T82nNDVaMbk,84654
260
+ torchrl\modules\llm\backends\vllm\vllm_plugin.py,sha256=q090DMIKRnUpzVM9csIS2uIv0IeZbtaAc_ND6SfXyQU,716
261
+ torchrl\modules\llm\backends\vllm\vllm_sync.py,sha256=_HDPI7m-AMAl7h6RwQDPFZvTFN6Nt74Ne8_fbHpGOx0,16869
262
+ torchrl\modules\llm\backends\vllm\vllm_utils.py,sha256=oWBPA7oyJmLXZ-nSqghggVmTlRCyVkV0TX5nGTyUFJA,4972
263
+ torchrl\modules\llm\backends\vllm\_models.py,sha256=DL5eYRG_gWzlD_v2e1JNCPTorHNiUcAV6wZoxsPj8gw,1403
264
+ torchrl\modules\llm\backends\vllm\__init__.py,sha256=Rs9bKslgQJux9i6raA0nVfOZE1kq-MUbjMJolg7oGIY,3021
265
+ torchrl\modules\llm\policies\common.py,sha256=r9GCshMtDEsoUXPHCtK4R1tpm6pWV_alFprQrKiOdsI,75019
266
+ torchrl\modules\llm\policies\transformers_wrapper.py,sha256=bjLPmv36Nx4rmAKV3_zh1vMtQuqa9XXfWXkqjgL7BRU,114845
267
+ torchrl\modules\llm\policies\vllm_wrapper.py,sha256=UlED_st13XWu36uqBsHwv9gmDpWkwPqGY3LqRgTv6f0,98528
268
+ torchrl\modules\llm\policies\__init__.py,sha256=0KjygrHwSqHRIggnf0IpmBahityI-s9-hoaEG0PDHIs,877
269
+ torchrl\modules\mcts\scores.py,sha256=uC_s9KeSEqUETkabSE3ZnBGFBNn89JCHMsFBGNWkyBs,23931
270
+ torchrl\modules\mcts\__init__.py,sha256=wkmczOIZdRUt8tj2mBwohS9ImpOih9V8oHgqD3qn6vE,441
271
+ torchrl\modules\models\batchrenorm.py,sha256=bR4ZhaJ5E1cSK5o8L2dNX5KVLIb-bgrYxcq6yhx0I1A,4869
272
+ torchrl\modules\models\decision_transformer.py,sha256=0ycW6aKaPgS8cTFEBCF5nMcVy4KdCswe1P2WIqBfSSU,6778
273
+ torchrl\modules\models\exploration.py,sha256=CklIbw5thOQvyGLqDSpZ8Elmc5maI-1M1ybO4wUoqdo,31341
274
+ torchrl\modules\models\llm.py,sha256=x5VS_K9PQUxKcRumWrPifeGRGgKh1IhB_08bSCRZe4o,6554
275
+ torchrl\modules\models\models.py,sha256=acqLy1Y7tqNyifPzMkMCdGIMXOf8NtCvjw0AKb331oE,67756
276
+ torchrl\modules\models\model_based.py,sha256=wh89F0exh9NJnT47Fx8hN7KGx8qN9cK4lpc0eu-rUK4,23707
277
+ torchrl\modules\models\multiagent.py,sha256=X3b1R-LQ6yRYTDqx_UMC3YIsPGGWYF9AxNrcXnHrsGo,45065
278
+ torchrl\modules\models\utils.py,sha256=h39uT7CVoLLT_G2jBq7-KX21OHlfx7ocomJ4SN1V3TY,5220
279
+ torchrl\modules\models\__init__.py,sha256=Y1XTkBOB5EMj6IaMru6V3CDwFLnkUtxzsHcqzeqq_4Y,1829
280
+ torchrl\modules\models\recipes\impala.py,sha256=7gdlBjFl0MFlEn6i81a2vL1o3s55oQyxZMu12Wv1On8,5852
281
+ torchrl\modules\planners\cem.py,sha256=r8YMnHMpwUMlUy1wnf6PGUXAqZFmihthXGLU1rStav4,9767
282
+ torchrl\modules\planners\common.py,sha256=5p_f9UdZsajCTLiS-qvlQf3s_QoOaR6RUPcxECDFAGk,2514
283
+ torchrl\modules\planners\mppi.py,sha256=hXvdF2GNNfOhKKTd6xJ0TsdvsFXnspX8wM73EqPXDR0,11034
284
+ torchrl\modules\planners\__init__.py,sha256=ZXaI0YMCN7fSex619aaQ7MsQ-NsNJuXuVKcCp4_MxI8,342
285
+ torchrl\modules\tensordict_module\actors.py,sha256=SaYeX2FPTF1wjhlkmZf6eUeHI6oirE9CsPs0nH7JFsQ,111183
286
+ torchrl\modules\tensordict_module\common.py,sha256=Y0MmOh2-HXlm1T0QkCCa8XpPw1rGB3iTMm4-k3hqGzY,22236
287
+ torchrl\modules\tensordict_module\exploration.py,sha256=lb3_Q9Uob_LeKpD5oYIMWGVnGmPDxqJCCDkc285wrjs,32974
288
+ torchrl\modules\tensordict_module\probabilistic.py,sha256=qUGme7BNgK0l2ALqkh7bekFNaoxRKApmPm6HbzZ8ZB0,16679
289
+ torchrl\modules\tensordict_module\rnn.py,sha256=On9tV5JGrG3wblllX5dsqonmRwP_1dQvG8k-c__vP-0,67370
290
+ torchrl\modules\tensordict_module\sequence.py,sha256=UMyPgl1XhgbL70orZISjM1spQ1NT1bejNpATAlODcu8,6143
291
+ torchrl\modules\tensordict_module\world_models.py,sha256=r1PlCgKY4UKMhJh5ksIzmuSA9BbOAan1-ptVTuMFCD4,1394
292
+ torchrl\modules\tensordict_module\__init__.py,sha256=8BlbcocePw2qpN1QepUDAZApVsFiQy2VFYsHMcUS-gI,2423
293
+ torchrl\modules\utils\mappings.py,sha256=HEPGNHhQrPNU85-Bq0cYm1TZIhSkdEBkLvgrmjFMa4Q,371
294
+ torchrl\modules\utils\utils.py,sha256=Ae2bl6GDxm9kU73WeLi-0ZEsrFt-XTaGqdxdXiX9LSU,3005
295
+ torchrl\modules\utils\__init__.py,sha256=NQ_ko0JAIPY_X5RgBJnZLZXnYSH2q_kuD0tvXGqqY3k,1165
296
+ torchrl\objectives\a2c.py,sha256=9Bb6GZPwieVU28RuO-WixBIzxiOm6-Qc8yM0x1V--ZA,29230
297
+ torchrl\objectives\common.py,sha256=608Lxg2dcfdMlHnlo-A0f-PwRMoRzT_Vd85xWUjq1wk,31846
298
+ torchrl\objectives\cql.py,sha256=4SeLqC5YKfDuNLAhoXYuVpTikC6rd_i4uDKRNlvQWss,56967
299
+ torchrl\objectives\crossq.py,sha256=W3AqOTDdaGrK3wRrRexv_JlEp51_U3LbX1e8DTSi1jw,29950
300
+ torchrl\objectives\ddpg.py,sha256=lNLul-tr1sGp2pfRxj110V4rQ3baA09rH96nedKugYQ,19021
301
+ torchrl\objectives\decision_transformer.py,sha256=eAMgI50zs6pgtCktBopKAEi6iU6VWLfNIwmZ1c6NzW0,13466
302
+ torchrl\objectives\deprecated.py,sha256=hqYcApjHrO0pZqrHSJY33sHjrgE176d3Rz-4bADCh9I,21618
303
+ torchrl\objectives\dqn.py,sha256=YEcthBDfPnJHSH48Jhc5eTgjTJwMphw3FM1W82kTSpY,30472
304
+ torchrl\objectives\dreamer.py,sha256=Eo8mhuQTOtTI85NWhnizO6ToBqw2ah9s-ZblWmmEigU,19443
305
+ torchrl\objectives\functional.py,sha256=0Pr_debAMM2bp06HPGVIpLTcyBue4DvcyUJVsaa6AjE,2154
306
+ torchrl\objectives\gail.py,sha256=MCJ-TE_asCp-NTfSgrqkUx9DWrR1GXth7VqrH46lndA,9855
307
+ torchrl\objectives\iql.py,sha256=aFeMWRf1hEC3u_RN8jn9oFNc_kbxE2cWDLX-fm4Z5ZQ,44402
308
+ torchrl\objectives\ppo.py,sha256=XB6eiHEJxN0LtzwHDOp6Qs-2XHt62s_2kXq-hYuGUwQ,81962
309
+ torchrl\objectives\redq.py,sha256=H76oRz3SgoRgNgJoKn2_mLz0F-QI6zfN0k8UFWbhTMQ,29616
310
+ torchrl\objectives\reinforce.py,sha256=3KifuDGjDdbxA-yW3FDUGTTpenDg_LPIBj7i0z0Oh7o,23212
311
+ torchrl\objectives\sac.py,sha256=jQkyW1p1NjTGxAt0b5tvn42zmS9yr8FwXxX_1ScYv4Y,70015
312
+ torchrl\objectives\td3.py,sha256=zOkRbrltIcKVgstE-ievnUeE3j7PFKoNQ7Ni7KD0tsY,24443
313
+ torchrl\objectives\td3_bc.py,sha256=1Uzo7sX9cxLedabYlU1dNYM0n02aQIentyPcdF4vVSU,27258
314
+ torchrl\objectives\utils.py,sha256=pcIWoQQSyRkR_crdjdv9k66D7uBmkVKIllrPgSfwGdc,27940
315
+ torchrl\objectives\__init__.py,sha256=Ug1FX1kFbTSz_i51uaDw7pOBIXSUIbH7BE5_8PZNbHM,2245
316
+ torchrl\objectives\llm\grpo.py,sha256=NZpXodJi3BYf8mWmp_i728OebUTfIrjUhc-jrUcwNsk,39000
317
+ torchrl\objectives\llm\sft.py,sha256=C6ZcTVGlAksZJJ_MK4721qNUiVg0p_3Dekg6VnrI03M,21365
318
+ torchrl\objectives\llm\__init__.py,sha256=R6_1jv0Is0oJ6O4bsNSPWtx6ajb7nUWbPPcstX46HBA,646
319
+ torchrl\objectives\multiagent\qmixer.py,sha256=EWtgINDkz1-iHai7QXMfHDHmOeEh2HLAyDrxhSUVp1w,17694
320
+ torchrl\objectives\multiagent\__init__.py,sha256=5uebDe5KrvlzeYV_BSd5vdmfruJQYMeDVVbU4iHErEg,245
321
+ torchrl\objectives\value\advantages.py,sha256=mc_xmL3JwmXvYt5N_mPsGW-cr0-HWjsGKCG_uy5mP2E,87234
322
+ torchrl\objectives\value\functional.py,sha256=ZKC5_ckrOy_oacFjnfAdjEiJbuozBN8eWMADvt6I2Ik,52731
323
+ torchrl\objectives\value\utils.py,sha256=EQV-JnWspJcclHssgGXjvVWhgFmlJzep8E_SIPgA6qQ,13616
324
+ torchrl\objectives\value\__init__.py,sha256=QkSnenYVqe_3FVtwGr_D86N52unnpBvRXfcC5JFTBOw,589
325
+ torchrl\record\recorder.py,sha256=YJmyHyC0TyhivLJALbDsdCMCut16h7BMd1YLbRi-vlk,22936
326
+ torchrl\record\__init__.py,sha256=ktfH9AgjJ4NnTSR7FXAEcXRYtZHkPtwcxlGNDkLLEOw,523
327
+ torchrl\record\loggers\common.py,sha256=GLC6wUv40rTHyiZQ1-YQnauuqk6oqrkRGsDV0ZCbVQA,1234
328
+ torchrl\record\loggers\csv.py,sha256=uNFjiPLq7mMr5z2WPyjyr9HGexu4ZkUwbX09FsV1mJ4,9524
329
+ torchrl\record\loggers\mlflow.py,sha256=9N-a5OUJJGwYej0WvTxQPkrazsahhmgof8seMDCnjM0,5098
330
+ torchrl\record\loggers\tensorboard.py,sha256=x1Mo7KE4-iGG5NVToAP-1XceG_F6Vipr26B_1CK9Tg0,5005
331
+ torchrl\record\loggers\trackio.py,sha256=xb9Nmp5MAT5pRP0YKRe4KOLjrzxzHGLwYIJrU-CrY_k,5236
332
+ torchrl\record\loggers\utils.py,sha256=XgpYzii8pRUAVLXa-dxJHgVckluAK0-7WTXCGPn-Xag,2790
333
+ torchrl\record\loggers\wandb.py,sha256=uZUAAfXyqRCY82TGDTrJe-KfQuR4ZY-d7fRucxRdyM8,7753
334
+ torchrl\record\loggers\__init__.py,sha256=pa6ttxj0FORHS6MgiYg05iFoABwJ8vqBHn45wkqshT4,568
335
+ torchrl\services\base.py,sha256=l-zIhYPxWIYCaLdJ0cK2Z3ccTFE4wO7ztvPhHq0gf_g,3713
336
+ torchrl\services\ray_service.py,sha256=DhuGtk7SR39EKw810XCTNusC-3_CsKgBYQY_covMTho,16419
337
+ torchrl\services\__init__.py,sha256=X2rGd6ALWFTRIJ7vkTk8kBliT0gNon1kX1RZ5kFvI10,2854
338
+ torchrl\testing\assertions.py,sha256=lxUrXgRIOaavMG0GNKRj1UmdJO--E5dyq24T7RLtTQU,7603
339
+ torchrl\testing\dist_utils.py,sha256=jafuVgxz4Y1_l0bVSV90r2god__pCI-NYpCLzbLNmfk,3926
340
+ torchrl\testing\env_creators.py,sha256=pu2QpTIouf6a0DAZhyZlyhgT6eRpxyWmcB3ZoxI5UW0,6817
341
+ torchrl\testing\env_helper.py,sha256=KhWykrn45QpJtlYbwjRL1ja1Hmp40IlJBfJ83MWFLr4,1237
342
+ torchrl\testing\gym_helpers.py,sha256=SqKAmZX2Rvpr-dFArcIRegnF7bcdL6nW7gATkzk_410,5203
343
+ torchrl\testing\llm_mocks.py,sha256=GlbLoO5tr5naUQLwfLj9MVaAyXUpM8JUMcdTSz7qI3g,4377
344
+ torchrl\testing\mocking_classes.py,sha256=h1z1TbLEgbvKmVCdjKSI83lIVSfxu_lq-fqFlIJSo34,95423
345
+ torchrl\testing\modules.py,sha256=3pQEKT5OzRhK5eKJVsslqFORXrsYSC-94C-QoIPV6v0,10972
346
+ torchrl\testing\mp_helpers.py,sha256=OpQBvviCR99ZM-N2aTxG5vtEAo7_iIctfTbCGFO90rg,413
347
+ torchrl\testing\ray_helpers.py,sha256=anHGoH3wHhKHxdEOn13QysS0kXNs5mG-8FMEB8dYfvA,10399
348
+ torchrl\testing\utils.py,sha256=4c_AcaOAjUCv1F9fhlDHSaIoyiHyItSaVqNtTi1uHnk,5448
349
+ torchrl\testing\__init__.py,sha256=qZDrj7NMI0F27kYHv5NC2qZgJFo_LCQ-HLwVH61VC28,2659
350
+ torchrl\trainers\trainers.py,sha256=Xnm_LvkAXfkndIRkpIQQ6ao9iSxYA4_YtzCgUBBVKZ8,81059
351
+ torchrl\trainers\__init__.py,sha256=pW39addrKWeDx4XiA6nlot8UWLdIiBmAR6hSFP93zpI,909
352
+ torchrl\trainers\algorithms\ppo.py,sha256=2lynrSoKRellRjrRrCDBFAxFqU7wLbjz7vNUkAyLmv0,15773
353
+ torchrl\trainers\algorithms\sac.py,sha256=NwES0iha7yU-NhIv3yqNH0fCuQlMCfo0OUEJ0IAHH1Y,13368
354
+ torchrl\trainers\algorithms\__init__.py,sha256=adWPuQ4U91Ocv4kwCmf1_pZqBp8O7iubHxr4GeIZ37k,323
355
+ torchrl\trainers\algorithms\configs\collectors.py,sha256=9b-0IJQVkT3B9cUNrT0xNst6ygyf7UdBOAR5lCzrpkI,7105
356
+ torchrl\trainers\algorithms\configs\common.py,sha256=Gydbb7tqDPeeJBrqImyQjMylmZjN6zUUirNAxv1ZSRA,1164
357
+ torchrl\trainers\algorithms\configs\data.py,sha256=4VgPLUzDpiTXyytyJzPbrH1xhYXG2oPyTUz0U6h8hOw,9062
358
+ torchrl\trainers\algorithms\configs\envs.py,sha256=cukLfY_8ZByXkeItkI42l5ieXUFQqbfJhb72I2IC1ls,3452
359
+ torchrl\trainers\algorithms\configs\envs_libs.py,sha256=bkeChDGO1ii3XaDsCgAaFTorNOO9rfLQxhDSNJeP5Jo,11116
360
+ torchrl\trainers\algorithms\configs\logging.py,sha256=3ENFIw6u05tYCqKhD9nFWjBKI6c3PsQ_3SrmpnG9V1M,1837
361
+ torchrl\trainers\algorithms\configs\modules.py,sha256=evnrVsGxyb7WNdgZcZtiLWABvM3PHntbPptpNOVizZM,18197
362
+ torchrl\trainers\algorithms\configs\objectives.py,sha256=RxSnzT-PJaDli5Taba57Dz8MGAuiRWyaTVun4-Gu_rQ,5557
363
+ torchrl\trainers\algorithms\configs\trainers.py,sha256=01YyPRYVIDnFbK16BPHZRCdjrH9FHUOheBp8a9kHLec,13753
364
+ torchrl\trainers\algorithms\configs\transforms.py,sha256=zZB4KaX8EOEuOWKcJaFK0imq3MQ59e6u17OhK97VV1I,29768
365
+ torchrl\trainers\algorithms\configs\utils.py,sha256=7_MNQDYBxjEVYDLU-iQwuFtAja9E2X-o287zMEVKwAg,6942
366
+ torchrl\trainers\algorithms\configs\weight_sync_schemes.py,sha256=e62USmN9TP_VEox-7BhI4tB8q_ObrXSym301xQ-S9PM,6756
367
+ torchrl\trainers\algorithms\configs\weight_update.py,sha256=bvG_yBOZpRKBV8YT7vRxY3AtAvlNKkfPTWPK9VDxLNU,5098
368
+ torchrl\trainers\algorithms\configs\__init__.py,sha256=-4f9AS2y6nQMPkiIjIWSnz1LR_Tx99C2vBFkNYSjW20,26958
369
+ torchrl\trainers\helpers\collectors.py,sha256=XQjg1D2CptnlUUYGOc8hERDNSNGzfHAOibhoKyEkfz4,19076
370
+ torchrl\trainers\helpers\envs.py,sha256=oES17oyBU4ybknbPfKQLfvAijoVpa6-vcNmi5ORjufQ,22694
371
+ torchrl\trainers\helpers\logger.py,sha256=R0VDtxDINaT7e_TXs-BfxhmqWzwVyIhBoFV16QWf2Ws,1311
372
+ torchrl\trainers\helpers\losses.py,sha256=HwrovwbMOhY-5-hlOz-YHclKnoJhMijVjDNuATsfaos,5404
373
+ torchrl\trainers\helpers\models.py,sha256=VujBq9H92sEzpCtU1iTrJQNlwvyOO-Rho4bzsMonX6s,22465
374
+ torchrl\trainers\helpers\replay_buffer.py,sha256=RaZqXnHimmadiibvDBcLbtIhpPaVMTPhYMOBvX4v3CA,2060
375
+ torchrl\trainers\helpers\trainers.py,sha256=uTniRupp4taw2pCtAdY6YP1sPSgmKaRjug1KDNnC9aY,12322
376
+ torchrl\trainers\helpers\__init__.py,sha256=sCBIXQqFQKRrbcNojgPxIh82HpXnXKgA_kMa3uZESSk,1137
377
+ torchrl\weight_update\utils.py,sha256=uQOgPKyIo6qBgjJ-wYOuEmqISF8_SUQczAYQaoxPIaI,2907
378
+ torchrl\weight_update\weight_sync_schemes.py,sha256=ZpgcAsuk4euXcT7TIy75cZ2F_B0z0nHDj6iUyuQr9X0,43835
379
+ torchrl\weight_update\_distributed.py,sha256=EeMI5c84sxMtfJO4zy9p5KLNNMI5Qhv3pcOmle2M54s,29150
380
+ torchrl\weight_update\_mp.py,sha256=i9RHmmZHklix7USZLeEtqgf1BQERDv8Firo3lvi0_Gc,26670
381
+ torchrl\weight_update\_noupdate.py,sha256=fQlGCQ9iEFb29lORSTmUsYSLPW4L6F6MJb8rv-z8lZ8,3103
382
+ torchrl\weight_update\_ray.py,sha256=oYqeQZMFqyAJ68t2H3VFmJRo5OJZ7SOsmFEJ_2tAet8,38295
383
+ torchrl\weight_update\_rpc.py,sha256=agEjfQcgX0-FrFhAwwAvoTzYZ6mVQ-Raf1c1G7npgoI,10868
384
+ torchrl\weight_update\_shared.py,sha256=Rs8qqXEGLLgd7r1l0qX6zr4yRS4sBIS4dLfg3Pz8WT4,37514
385
+ torchrl\weight_update\__init__.py,sha256=keE0nXXLjcnh7BXyqIj2Hh9GoDhD2g8NCBsIGvIcZ4A,1135
386
+ torchrl\weight_update\llm\vllm_double_buffer.py,sha256=imXevzw8P1YmGzvNc4AQO9wtIsNYYRMOUNgsmjTDmzQ,13933
387
+ torchrl\weight_update\llm\vllm_nccl.py,sha256=-1cn4vEFJ0h5AyaTIogdDZHPKUtKDCPBbgyApYnioq0,27730
388
+ torchrl\weight_update\llm\__init__.py,sha256=hCOSruMG1xXwPylAAKyP3JGnKSbQXvPfpKgWFKmvHpQ,895
389
+ torchrl-0.11.0.dist-info\entry_points.txt,sha256=kjqZUboF3jzU21uy15NPn2WDfbwGE21Ls0fmfhqhmy4,110
390
+ torchrl-0.11.0.dist-info\LICENSE,sha256=PGO-oZsq4EzhE1-WQS2xGiEF3UCVb9YawfQ09cIMV_8,1119
391
+ torchrl-0.11.0.dist-info\METADATA,sha256=NkKzY_CqfTqDyrWCR_UW4rekSBLa-MngaC_JP82W7-I,50926
392
+ torchrl-0.11.0.dist-info\RECORD,,
393
+ torchrl-0.11.0.dist-info\top_level.txt,sha256=niUu8mZaEt1Z9cX9Mv7FQF9PCg3CTjUnjuqLA929JQ0,73
394
+ torchrl-0.11.0.dist-info\WHEEL,sha256=ehvDhPoJd3XGMR4zfhWDKK5BjYI3fGJZ9o8LOfljahk,101
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (72.1.0)
3
+ Root-Is-Purelib: false
4
+ Tag: cp314-cp314-win_amd64
5
+
@@ -0,0 +1,2 @@
1
+ [vllm.general_plugins]
2
+ fp32_overrides = torchrl.modules.llm.backends.vllm.vllm_plugin:register_fp32_overrides
@@ -0,0 +1,7 @@
1
+ benchmarks
2
+ build
3
+ gallery
4
+ scripts
5
+ sota-check
6
+ sota-implementations
7
+ torchrl